Chordogram

This chordogram shows the chords that the model has analysed from the chromagram. It shows that the track is prominently in c (correct) but it can’t figure out if it is in C major or Minor. This could be because the track consists basically of only the c note which means the model can’t distinguish the mode any further than that. Further more the model seems to struggle in the chorus. This is to be expected as the chroma gram in this time frame is messy as well and this visualisation is based on that (already a bit messy) chroma gram.

Chromagrams

This is a chromagram of my original track. Most of the track is C dominant which is correct. Interesting: from 50-80 seconds there’s some higher notes, this corresponds to my song which drops at that point and starts playing harmonies. also from 150-170 there’s a lot more c than normal, this is because there’s a very high note playing a c as well as the rest of the track.

Cepstrograms

Chroma SSM

The Chroma SSM shows that most of the song is quite similar in key and it shows that there are a lots of little moments of uniqueness in both of the chorus’. It could be that the software struggles with the organs in the track, which may be percieved as slightly offkey because they sound a bit detuned.

The timbre SSM is interesting as it cleary shows that when the breakdowns are happening. in the 20-40 and 125-150 there are breakdowns which are similar in timbre, since they have the same absence of drums.

The Computational Musicology Dataset Explained

The following data set provides a detailed breakdown of key musical features for each track in it. The tracks are part of a collection (corpus) of music which is either composed by students of computational musicology, generated by AI or existing royalty free music. The features in the table below, just like their assigned values, were retrieved from essentia, an open-source C++ library for audio analysis and audio-based music information retrieval. All the tracks in the table have been analysed by this program which gave these results. Here is an explanation for what all the features mean:

  • Approachability reflects how pleasant and easy a song is to listen to,

  • Arousal measures its energy level, with higher values indicating more intensity.

  • Danceability assesses how well a track is suited for dancing, based on rhythm, beat strength, and tempo.

  • Tempo is a feature which indicates the speed of the song, measured in beats per minute (BPM).

  • Engagingness shows how likely a track is to hold the listener’s attention.

  • Instrumentalness estimates the presence of vocals, with higher values suggesting more instrumental content.

  • Valence describes the overall mood of the song, where higher values correspond to more positive and cheerful tones, while lower values indicate a more subdued or serious sound.

These features together provide a clear overview of each track’s musical profile, making it easier to analyze and compare songs.

filename approachability arousal danceability engagingness instrumentalness tempo valence
ahram-j-1 0.4029289 3.201173 0.1089266 0.4353951 0.9052537 114 4.244095
ahram-j-2 0.9408180 4.379115 0.3010029 0.5765418 0.1853325 131 4.833456
aleksandra-b-1 0.3243975 5.954064 0.9829239 1.0266527 0.4294903 93 6.163685
aleksandra-b-2 0.3052886 4.052924 0.5063376 0.3771538 0.9149074 110 4.898212
berend-b-1 -0.0463543 5.635585 0.9943255 0.9576952 0.5347002 98 5.545103
berend-b-2 0.4914903 6.700513 0.9434316 1.0000600 0.4287079 103 6.044937
bram-d-1 0.3582040 3.649430 0.8970102 0.3560562 0.8373330 110 4.448651
bram-d-2 0.4568563 5.075095 0.4634000 0.7275821 0.5428896 86 5.386048
cecilia-b-1 0.7193086 4.141717 0.1389557 0.4921596 0.8516406 110 5.294700
cecilia-b-2 0.4901986 4.912464 0.6415554 0.7085047 0.7483985 69 5.156474
desmond-l-1 0.4008293 5.525241 0.6376823 0.8862919 0.7578623 93 5.837563
desmond-l-2 0.3221814 6.353199 0.9561019 1.0029999 0.5750142 100 5.886079
ellen-r-1.mp3 0.7052094 4.758742 0.5889034 0.6452620 0.4181556 69 5.194044
ellen-r-2.mp3 0.7052094 4.758742 0.5889034 0.6452620 0.4181556 69 5.194044
elze-s-1 0.4418911 6.440705 0.4217200 0.8871393 0.2283936 113 5.246190
elze-s-2 0.6260668 4.353893 0.1724735 0.6173213 0.3648041 125 4.790000
erik-l-1 0.4406818 3.112599 0.0468779 0.3450791 0.8849752 74 4.250600
erik-l-2 0.4909441 3.512280 0.2015236 0.3169740 0.8910435 104 4.458392
evan-l-1 0.3806048 4.050198 0.2035568 0.3683336 0.6760742 84 3.941779
evan-l-2 0.0897957 5.359808 0.7983584 0.9520752 0.6835271 93 4.708595
filip-z-1 0.2849498 3.504120 0.2340556 0.5244678 0.8991349 84 3.658526
filip-z-2 0.6010121 4.620215 0.3225434 0.6837600 0.5916834 125 5.262037
gijs-s-1 0.4068123 5.932812 0.9822546 0.9522422 0.7007251 90 6.052958
gijs-s-2 0.6554639 4.795954 0.2264639 0.4745934 0.7128631 83 5.172315
hidde-s-1 0.4232091 5.896144 0.9166474 0.9885877 0.6110775 97 6.040661
hidde-s-2 0.7248405 4.872188 0.8826922 0.7354387 0.8091347 138 5.394637
jasper-v-1 0.8997371 4.674417 0.3746580 0.5938324 0.2967478 134 5.068545
jasper-v-2 0.6123927 5.997169 0.3169810 0.7417597 0.2617876 116 5.466180
jelle-w-1 0.3466583 4.376393 0.2197819 0.4733819 0.7757404 30 4.249412
jelle-w-2 0.5007432 4.889252 0.4473473 0.6093664 0.5017543 132 4.765463
joppe-h-1 0.4716103 4.279476 0.5824611 0.6954765 0.6972030 94 4.925738
joppe-h-2 0.2176376 5.764420 0.9980006 0.9965415 0.6030746 176 6.007116
ke-w-1 0.7116295 4.798904 0.9735621 0.8119805 0.6178910 149 5.446843
ke-w-2 0.7057029 4.427266 0.2898834 0.5842432 0.6086771 131 4.761318
lennart-p-1 0.7290038 5.006702 0.1393297 0.6388944 0.7214542 124 5.326187
lennart-p-2 0.6791568 5.259566 0.2441030 0.5233951 0.5980960 73 5.166692
lesley-n-1 0.8021904 4.486453 0.1582881 0.5203619 0.6320138 80 5.250509
lesley-n-2 0.5466217 4.250094 0.5850586 0.5209269 0.8077224 131 4.905036
lo-l-1 0.3330394 3.132553 0.1232146 0.3578993 0.9554076 30 3.428586
lo-l-2 0.1741783 3.838783 0.3450872 0.4405148 0.8526388 144 3.714832
lucas-w-1 0.0420522 7.021555 0.8521489 1.0301197 0.2178714 110 5.810045
lucas-w-2 -0.0087452 5.942399 0.8823236 1.0298319 0.4103830 114 5.197560
marit-r-1 0.4937623 4.817852 0.1733139 0.6132142 0.5142947 86 4.824087
marit-r-2 0.8854424 4.879700 0.2860056 0.5910115 0.3498075 83 5.514646
mees-k-1 0.3978606 4.908429 0.7849343 0.5642022 0.8105008 110 5.484569
mees-k-2 0.5005443 5.023745 0.2532089 0.6276894 0.5692230 83 4.918528
mette-l-1 0.2335947 6.181780 0.7528797 0.9903458 0.3876085 103 5.421827
mette-l-2 0.3252062 5.960568 0.8240567 0.9501317 0.5403929 95 5.860531
nora-k-1 0.4590537 5.095632 0.7594032 0.6804156 0.3324838 111 4.989901
nora-k-2 0.9406351 5.344668 0.8526822 0.7641367 0.2013702 134 5.443507
onni-q-1 0.8474047 5.031465 0.4094645 0.6266215 0.6974297 132 5.080364
onni-q-2 0.7957178 4.473717 0.2279108 0.5982016 0.6955491 84 5.170425
popke-s-1 0.1542392 5.028270 0.8301601 0.8979754 0.7648295 93 5.405690
popke-s-2 0.0156199 6.451765 0.9998716 0.9749477 0.5617048 96 5.769380
raphael-g-1 0.5182752 3.368581 0.1973290 0.4087600 0.8793966 30 4.176082
raphael-h-2 0.5083420 3.334759 0.1448293 0.3182925 0.9287950 77 4.643386
reinout-w-1 0.2596200 6.304508 0.9425499 1.0174429 0.4784729 90 6.285594
reinout-w-2 0.5909528 6.568566 0.9814444 0.9157294 0.1309513 103 6.402428
roemer-i-1 0.1390296 5.377656 0.9999970 0.7288911 0.5556484 138 5.465054
roemer-i-2 0.3957483 4.504606 0.9994513 0.5772333 0.7669997 85 4.934304
ruishan-h-1 0.6115500 4.038781 0.2289777 0.5076442 0.6317007 84 4.241537
ruishan-h-2 0.4429492 4.011900 0.3603345 0.5951134 0.7604732 86 4.248597
sanne-o-1 0.9580945 5.336050 0.3583764 0.7471432 0.5559838 121 5.709170
sanne-o-2 0.4933715 5.008964 0.8582797 0.8044644 0.5976899 83 5.399205
sanne-v-1 0.6348811 4.281034 0.6300172 0.6034411 0.1643667 86 4.658013
sanne-v-2 0.5268122 4.373618 0.7554580 0.6203578 0.1689946 124 4.370211
santiago-m-1 0.9081463 5.744700 0.8689661 0.9469227 0.2903972 128 6.075562
santiago-m-2 0.8426453 5.862379 0.9607697 0.9726217 0.4014053 134 6.387042
senn-v-1 0.7199484 5.687056 0.7085183 0.7244071 0.4772277 78 5.690660
senn-v-2 0.2145508 5.502037 0.7700977 0.8611157 0.4976678 110 5.188929
sven-n-1 0.6349754 4.376606 0.2689031 0.5351772 0.8316782 112 5.209647
sven-n-2 0.6768115 4.215839 0.1657857 0.5584868 0.5480993 124 4.810324
sytze-m-1 0.5347930 4.236442 0.2704742 0.7633239 0.7763491 117 5.115758
sytze-m-2 0.3873924 3.739505 0.1359031 0.5235139 0.8593549 77 4.646982
thijmen-g-1 0.2489275 5.282096 0.9601820 0.8954449 0.7789603 86 5.705674
thijmen-g-2 0.3224232 4.128485 0.5703917 0.6606441 0.8427449 112 4.762093
thomas-m-1 0.7148184 4.900313 0.9122813 0.6823866 0.3298571 117 5.218797
thomas-m-2 0.0507165 4.662500 0.9475483 0.9497138 0.8531966 90 5.550669
thomas-r-1.wav 0.6115435 3.673418 0.2521307 0.4021748 0.6166241 87 4.353166
thomas-r-2.wav 0.4777539 3.958385 0.4422260 0.4580720 0.6518382 81 4.509587
tobias-p-1 0.6921950 3.804785 0.1104574 0.2463361 0.8319886 77 4.442183
tobias-p-2 0.1653448 5.902356 0.4505573 0.9483601 0.5405050 104 4.300364
tymon-z-1 0.3397078 3.818913 0.1338143 0.5487939 0.9210021 30 3.961958
tymon-z-2 0.2361003 3.683670 0.1351216 0.1041139 0.8727902 30 4.012024
wednesday-w-1 0.6269138 4.879522 0.9911991 0.5430687 0.6506770 132 5.283437
wednesday-w-2 0.4706164 5.333390 0.9679925 0.8080030 0.4442444 88 5.536323
wietske-b-1 0.6037775 3.429294 0.2621410 0.3218339 0.7691792 96 4.341630
wietske-b-2 0.4123995 4.931853 0.9852258 0.6450658 0.6166019 102 5.297197
xuelong-f-1 0.1891619 5.399809 0.7916526 0.8638032 0.6764871 120 5.203136
xuelong-f-2 0.5753747 5.519013 0.8823883 0.8083547 0.5390321 83 5.637689

Positive correlation between danceability and engagingness

This is a graph which has mapped the engagingness of each song compared to its danceability. The colour scale is based on the tempo of each song. The first noticable aspect of the graph is the seemingly positive correlation between danceability and engagingness which is shown by the red trend line. On average it is clear that in most cases a high danceability value means that same song will have a high engagingness rating aswell. From the colour scaling it can also be noticed that most songs that have high scores for those features also have a higher tempo. This could mean that those features are highly correlated or that the way essentia measured these features is similar in terms of computational analysis. It would be interesting to look at why this correlation seems to be in place, for instance through examining the roll of instrumentallness, or genre in combination with this analysis.

The two points that are highlighted are a song I arranged by myself and one I genreated with suno. What can be seen with these songs is that my own song performs higher in both danceability and engagingness than the ai song while they are the same genre and made with the same intention. Secondly the bpm on the AI track is acurately analysed while the one for my song is not, which could also be an interesting way of analysing the data: can ai analyse ai songs better than human made songs?

Information on my sumitted tracks

Hidde-s-1:

I produced this song myself. I make music with clubs or festivals in mind as I like to DJ. For this track I tried to combine a mainstream house music sound and combine it with some more raw electronic sounds.

Hidde-s-2:

This is a track I generated with Suno. I asked chat gpt what the key characteristics of a dance track in a sweaty club in Amsterdam were:

“Punchy four-on-the-floor kick, deep rolling bass, crisp shuffled hi-hats, sharp claps, detuned wide synth leads, tension-filled breakdown, rising FX, massive sidechained drop, high-energy, club-focused groove.”